Temporal Event Grounding on E.T. Bench Grounding
60.2TVG F1D²VLM-3.8B
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| D²VLM-3.8BYear=ICCV’252025.12 | 60.2 | 14.4 | 33.4 | 35.2 | 68.2 | 42.3 | |
| Qwen2.5-VL-7BYear=arXiv’25, Implementation=Implemented by this paper authors2025.12 | 46.6 | 9.3 | 32.2 | 19.9 | 68.6 | 35.3 | |
| E.T.Chat-3.8BYear=NeurIPS’242025.12 | 38.6 | 10.2 | 30.8 | 25.4 | 62.5 | 33.5 | |
| TimeChat-7BYear=CVPR’242025.12 | 26.2 | 3.9 | 10.1 | 29.1 | 40.5 | 22 | |
| LITA-13BYear=ECCV’242025.12 | 22.2 | 4.6 | 18 | 29.7 | 23.9 | 19.7 | |
| VTG-LLM-7BYear=AAAI’252025.12 | 15.9 | 3.7 | 14.4 | 26.8 | 48.2 | 21.8 | |
| VTimeLLM-7BYear=CVPR’242025.12 | 7.6 | 1.9 | 18.2 | 15.9 | 28.9 | 14.5 | |
| Video-ChatGPT-7BYear=ACL’242025.12 | 7 | 1.3 | 15.1 | 8.4 | 28.8 | 12.1 | |
| Video-LLaVA-7BYear=EMNLP’242025.12 | 7 | 1.9 | 15 | 0.3 | 28.9 | 10.6 | |
| PLLaVAYear=arXiv’242025.12 | 6.9 | 1.1 | 5.7 | 0.3 | 28.9 | 8.6 | |
| LLaMA-VID-7BYear=ECCV’242025.12 | 5.5 | 1.2 | 8 | 1.4 | 30 | 9.2 | |
| Video-LLaMA-2-7BYear=arXiv’242025.12 | 0.1 | 0 | 0 | 0 | 1.5 | 0.3 |